A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Bobo Li, Hao Fei, Tianjie Ju, et al.
OmniScientist is an end-to-end omni-modal AI scientist that conducts multidisciplinary research directly from heterogeneous raw evidence via a perception layer and three autonomous agents.
Lin Zhang, Lei Zhang, Xuanqin Mou, et al.
FSIM proposes a full-reference image quality metric using phase congruency and gradient magnitude as complementary features, achieving state-of-the-art correlation with human perception.
Unknown
This paper presents a language-guided long-horizon manipulation framework for multistep cloth folding, combining LLM-based planning with visual perception.
Zhen Fang, Yu Zeng, Wenxuan Huang, et al.
Video-DeepResearch extends multimodal agents to continuous video streams with a decoupled perception-exploration pipeline, achieving SOTA 64.0% on a new benchmark.
Unknown
Introduces Blink, a benchmark for multimodal LLMs focusing on core visual perception abilities, with tasks that are easy for humans but challenging for current models.
Unknown
Introduces Action Reasoning Models (ARMs), a robotic foundation model class with a structured three-stage pipeline integrating perception, planning, and control.
Simon Bruno Egli, Armon Arpagaus, Simon Adrian Amacher, et al.
A cross-sectional survey of Swiss clinicians reveals frequent LLM use (32.8%) with limited workplace guidelines, highlighting gaps in safe adoption.
Lizhi Yang, Junheng Li, Aaron D. Ames
PAC-MAN couples control-barrier safety with perception-aware training for whole-body humanoid dodgeball, achieving 95% real-world evasion with a fixed camera.
Unknown
This paper introduces a method to teach vision-language models 3D perception and reasoning by transforming 2D image inputs into 3D spatial representations.
Unknown
This paper introduces ContextAgent, a proactive LLM agent that leverages open-world sensory perceptions to initiate tasks without explicit user instructions.
Feng Xiong, Leyan Xue, Hongyu Lin
Introduces Perception-Correction Distillation (PCD), a label-free method that uses downstream failure and teacher-student disagreement as complementary witnesses to correct perception failures in multimodal reasoners.
Daniel Bolya, Po-Yao Huang, Peize Sun, et al.
Perception Encoder is a vision encoder trained via contrastive vision-language learning that achieves state-of-the-art results across diverse tasks by extracting strong general embeddings from intermediate layers.